Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3127 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2045. Min Range: -5.2045
Max Act: 5.2045. Min Act: -0.1700
Data Index: 1917398 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2045. Min Range: -5.2045
Max Act: 5.1733. Min Act: -0.1700
Data Index: 3604585 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2045. Min Range: -5.2045
Max Act: 5.1420. Min Act: -0.1700
Data Index: 1034362 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2045. Min Range: -5.2045
Max Act: 5.1420. Min Act: -0.1700
Data Index: 1114264 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2045. Min Range: -5.2045
Max Act: 5.1108. Min Act: -0.1700
Data Index: 8137850 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2045. Min Range: -5.2045
Max Act: 5.1108. Min Act: -0.1700
Data Index: 5211172 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2045. Min Range: -5.2045
Max Act: 5.0795. Min Act: -0.1700
Data Index: 2073048 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2045. Min Range: -5.2045
Max Act: 5.0483. Min Act: -0.1700
Data Index: 4314849 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2045. Min Range: -5.2045
Max Act: 4.9545. Min Act: -0.1700
Data Index: 7279037 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2045. Min Range: -5.2045
Max Act: 4.8920. Min Act: -0.1700
Data Index: 1403198 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2045. Min Range: -5.2045
Max Act: 4.8295. Min Act: -0.1700
Data Index: 6529772 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2045. Min Range: -5.2045
Max Act: 4.7983. Min Act: -0.1700
Data Index: 6815996 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2045. Min Range: -5.2045
Max Act: 4.7045. Min Act: -0.1700
Data Index: 420217 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2045. Min Range: -5.2045
Max Act: 4.6733. Min Act: -0.1700
Data Index: 172548 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2045. Min Range: -5.2045
Max Act: 4.6420. Min Act: -0.1700
Data Index: 7451563 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2045. Min Range: -5.2045
Max Act: 4.6108. Min Act: -0.1700
Data Index: 6228450 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2045. Min Range: -5.2045
Max Act: 4.5795. Min Act: -0.1700
Data Index: 3186188 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2045. Min Range: -5.2045
Max Act: 4.5795. Min Act: -0.1700
Data Index: 4561427 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2045. Min Range: -5.2045
Max Act: 4.5795. Min Act: -0.1700
Data Index: 2006032 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2045. Min Range: -5.2045
Max Act: 4.5795. Min Act: -0.1700
Data Index: 4458442 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19